Smart Connected Bikes

Bicycle manufacturing currently falls behind the rapid technological developments in automotive industries. We propose to design, develop and test a smart cycling eco-system where bicycles communicate in real-time with each other, and with the urban transport infrastructure (e.g. traffic lights) to optimize the use and improve traffic safety, economical value, and efficiency.

This require technologies and mechanisms to allow monitoring the bike, understanding the cyclist and the context, as well as data sharing between cyclists, industry, service providers, government, and urban planners. The new eco-system can drive decision-making, behaviour incentivisation, and ultimately investment, across government, and beyond. A key ingredient is an AI-enabled IoT ecosystem in which data is securely collected, shared, processed in combination with other data sources, and made available to establish new services. This allows to reliably identify relevant events (like dangerous situations), detect trends (like decreasing performance of components, allowing maintenance to be performed in time), and give new insights to the user (such as health and performance).


  • Smart industry
  • IoT
  • Data analytics
  • Situational awareness
  • Multi-modal sensing
  • Edge computing

Program objectives

A bike-centred embedded sensing platform will be designed to provide real-time information about the condition of the bike, the condition of the cyclist (movement and biking effort), interaction between the bike and the cyclist (pedalling, speeding, braking), interaction between cyclists as well as between cyclists and fixed (traffic lights) and moving objects (cars) around them. This involves developing a bike-centred multi-modal wireless communication platform. Through utilization of sensor fusion and outlier detection on streaming data collected by the bike platform, machine learning techniques will be developed that can detect and characterize danger that can trigger operational measures such as personalized intervention and maintenance tasks of the bike.


  • University of Twente (lead manager)
  • Saxion
  • TU Delft
  • Accell Group N.V.
  • TNO


2020 - 2024

More information


Dr. Jeroen Linssen

Associate Professor

06 - 8278 4767 LinkedIn


This project is part of the Smart Industry-program of NWO.